Jillian2017
Jillian2017
Very appropriate your timely and generous reply. For answer1: I also have no idea about the nosie mentioned in the paper, thanks for sharing your idea here. Have you ever...
Okay, I got. I will train ADE20k again without semantic map and with VGG loss. Thanks a lot.
@chenxianghu hi, do you add nosie while training the ADE20K, I came across an error result from the mismatch of the noise's dimension and the encoder network's output. So I...
Hi @ChenxiTU, when running the encopy.py, i come across a error :TypeError:super( ) takes at least 1 argument(0 given) in binarizer = network.Binarizer( ), the super() function is in modules/sign.py....
I got，thanks.
@alexgo1, yeah, I find it, thanks a lot.
@buaa-luzhi I cannot load the pretrained model from Dropbox. Would you send them to me, my email is [email protected], thanks very much.